Home

Description

llama.cpp is an inference of several LLM models in C/C++. Integer Overflow in the gguf_init_from_file_impl function in ggml/src/gguf.cpp can lead to Heap Out-of-Bounds Read/Write. This vulnerability is fixed in commit 26a48ad699d50b6268900062661bd22f3e792579.

PUBLISHED Reserved 2025-07-07 | Published 2025-07-10 | Updated 2025-07-10 | Assigner GitHub_M




HIGH: 8.9CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:P

Problem types

CWE-122: Heap-based Buffer Overflow

CWE-680: Integer Overflow to Buffer Overflow

Product status

< 26a48ad699d50b6268900062661bd22f3e792579
affected

References

github.com/...ma.cpp/security/advisories/GHSA-vgg9-87g3-85w8

github.com/...ommit/26a48ad699d50b6268900062661bd22f3e792579

cve.org (CVE-2025-53630)

nvd.nist.gov (CVE-2025-53630)

Download JSON